Elbow trauma in children: development and ...
Document type :
Compte-rendu et recension critique d'ouvrage
Title :
Elbow trauma in children: development and evaluation of radiological artificial intelligence models
Author(s) :
Rozwag, Clémence [Auteur]
Centre Hospitalier Régional Universitaire [CHU Lille] [CHRU Lille]
Valentini, Franck [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Scool [Scool]
Cotten, Anne [Auteur]
Centre Hospitalier Régional Universitaire [CHU Lille] [CHRU Lille]
Demondion, Xavier [Auteur]
Unité de Taphonomie médico-légale et Anatomie - ULR 7367 [UTML&A]
Centre Hospitalier Régional Universitaire [CHU Lille] [CHRU Lille]
Preux, Philippe [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Scool [Scool]
Jacques, Thibaut [Auteur]
Centre Hospitalier Régional Universitaire [CHU Lille] [CHRU Lille]
Centre Hospitalier Régional Universitaire [CHU Lille] [CHRU Lille]
Valentini, Franck [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Scool [Scool]
Cotten, Anne [Auteur]
Centre Hospitalier Régional Universitaire [CHU Lille] [CHRU Lille]
Demondion, Xavier [Auteur]
Unité de Taphonomie médico-légale et Anatomie - ULR 7367 [UTML&A]
Centre Hospitalier Régional Universitaire [CHU Lille] [CHRU Lille]
Preux, Philippe [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Scool [Scool]
Jacques, Thibaut [Auteur]
Centre Hospitalier Régional Universitaire [CHU Lille] [CHRU Lille]
Journal title :
Research in Diagnostic and Interventional Imaging
Publisher :
Elsevier
Publication date :
2023-04-29
ISSN :
2772-6525
English keyword(s) :
X-ray
Elbow
Pediatrics
Deep Learning
Convolutional neural networks (CNN)
Elbow
Pediatrics
Deep Learning
Convolutional neural networks (CNN)
HAL domain(s) :
Sciences du Vivant [q-bio]/Médecine humaine et pathologie
English abstract : [en]
Rationale and Objectives: To develop a model using artificial intelligence (A.I.) able to detect post-traumatic injuries on pediatric elbow X-rays then to evaluate its performances in silico and its impact on radiologists' ...
Show more >Rationale and Objectives: To develop a model using artificial intelligence (A.I.) able to detect post-traumatic injuries on pediatric elbow X-rays then to evaluate its performances in silico and its impact on radiologists' interpretation in clinical practice. Material and Methods: A total of 1956 pediatric elbow radiographs performed following a trauma were retrospectively collected from 935 patients aged between 0 and 18 years. Deep convolutional neural networks were trained on these X-rays. The two best models were selected then evaluated on an external test set involving 120 patients, whose X-rays were performed on a different radiological equipment in another time period. Eight radiologists interpreted this external test set without then with the help of the A.I. models. Results: Two models stood out: model 1 had an accuracy of 95.8% and an AUROC of 0.983 and model 2 had an accuracy of 90.5% and an AUROC of 0.975. On the external test set, model 1 kept a good accuracy of 82.5% and AUROC of 0.916 while model 2 had a loss of accuracy down to 69.2% and of AUROC to 0.793. Model 1 significantly improved radiologist's sensitivity (0.82 to 0.88, P = 0.016) and accuracy (0.86 to 0.88, P = 0,047) while model 2 significantly decreased specificity of readers (0.86 to 0.83, P = 0.031). Conclusion: End-to-end development of a deep learning model to assess post-traumatic injuries on elbow Xray in children was feasible and showed that models with close metrics in silico can unpredictably lead radiologists to either improve or lower their performances in clinical settings.Show less >
Show more >Rationale and Objectives: To develop a model using artificial intelligence (A.I.) able to detect post-traumatic injuries on pediatric elbow X-rays then to evaluate its performances in silico and its impact on radiologists' interpretation in clinical practice. Material and Methods: A total of 1956 pediatric elbow radiographs performed following a trauma were retrospectively collected from 935 patients aged between 0 and 18 years. Deep convolutional neural networks were trained on these X-rays. The two best models were selected then evaluated on an external test set involving 120 patients, whose X-rays were performed on a different radiological equipment in another time period. Eight radiologists interpreted this external test set without then with the help of the A.I. models. Results: Two models stood out: model 1 had an accuracy of 95.8% and an AUROC of 0.983 and model 2 had an accuracy of 90.5% and an AUROC of 0.975. On the external test set, model 1 kept a good accuracy of 82.5% and AUROC of 0.916 while model 2 had a loss of accuracy down to 69.2% and of AUROC to 0.793. Model 1 significantly improved radiologist's sensitivity (0.82 to 0.88, P = 0.016) and accuracy (0.86 to 0.88, P = 0,047) while model 2 significantly decreased specificity of readers (0.86 to 0.83, P = 0.031). Conclusion: End-to-end development of a deep learning model to assess post-traumatic injuries on elbow Xray in children was feasible and showed that models with close metrics in silico can unpredictably lead radiologists to either improve or lower their performances in clinical settings.Show less >
Language :
Anglais
Popular science :
Non
Source :
Files
- document
- Open access
- Access the document
- article%20scientifique.pdf
- Open access
- Access the document